paper-with-me

Papers

Prospective Learning: Principled Extrapolation to the Future

2022-01-19 · Ashwin De Silva, Rahul Ramesh, Lyle Ungar, Marshall Hussain Shuler, Noah J. Cowan, Michael Platt, Chen Li, Leyla Isik, Seung-Eon Roh, Adam Charles, Archana Venkataraman, Brian Caffo, Javier J. How, Justus M Kebschull, John W. Krakauer, Maxim Bichuch, Kaleab Alemayehu Kinfu, Eva Yezerets, Dinesh Jayaraman, Jong M. Shin, Soledad Villar, Ian Phillips, Carey E. Priebe, Thomas Hartung, Michael I. Miller, Jayanta Dey, Ningyuan, Huang, Eric Eaton, Ralph Etienne-Cummings, Elizabeth L. Ogburn, Randal Burns, Onyema Osuagwu, Brett Mensh, Alysson R. Muotri, Julia Brown, Chris White, Weiwei Yang, Andrei A. Rusu, Timothy Verstynen, Konrad P. Kording, Pratik Chaudhari, Joshua T. Vogelstein

Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the assumption that the future will be identical to the past in distribution or change adversarially. But these assumptions can be either too optimistic or pessimistic for many problems in the real world. Real world scenarios evolve over multiple spatiotemporal scales with partially predictable dynamics. Here we reformulate the learning problem to one that centers around this idea of dynamic futures that are partially learnable. We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning. We argue that prospective learning more accurately characterizes many real world problems that (1) currently stymie existing artificial intelligence solutions and/or (2) lack adequate explanations for how natural intelligences solve them. Thus, studying prospective learning will lead to deeper insights and solutions to currently vexing challenges in both natural and artificial intelligences.

📄 PDF Abstract BibTeX arXiv:2201.07372

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningDecision Making

Similar Papers 제목 키워드 기반

Interventional Flow Matching: Prospective Dose-Response Forecasting with Velocity-Field Jacobian Regularization

2026-06-28 · Amirreza Dolatpour Fathkouhi, Justin Lee, Heman Shakeri arxiv

Predicting a patient's physiological trajectory under a planned treatment sequence is a prospective interventional problem, not standard time-series extrapolation. We study this problem in glucose management, where insul…

Extrapolation in Statistical Learning with Extreme Value Theory

2026-05-03 · Sebastian Engelke, Nicola Gnecco, Anne Sabourin arxiv

Extreme value theory provides rigorous theory and statistical tools for extrapolation in machine learning, particularly in settings where traditional methods struggle due to data scarcity in the tails. A broad range of t…

Anomaly Detection

Extrapolative-Interpolative Cycle-Consistency Learning for Video Frame Extrapolation

2020-05-27 · Sangjin Lee, Hyeongmin Lee, Taeoh Kim, Sangyoun Lee

Video frame extrapolation is a task to predict future frames when the past frames are given. Unlike previous studies that usually have been focused on the design of modules or construction of networks, we propose a novel…

Prospective Learning: Learning for a Dynamic Future

2024-10-31 · Ashwin De Silva, Rahul Ramesh, Rubing Yang, Siyu Yu 외

In real-world applications, the distribution of the data, and our goals, evolve over time. The prevailing theoretical framework for studying machine learning, namely probably approximately correct (PAC) learning, largely…

PAC learning

KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation

2022-05-20 · Ta-Chung Chi, Ting-Han Fan, Peter J. Ramadge, Alexander I. Rudnicky

Relative positional embeddings (RPE) have received considerable attention since RPEs effectively model the relative distance among tokens and enable length extrapolation. We propose KERPLE, a framework that generalizes r…

DiversityLanguage ModelingLanguage ModellingPosition